151 citations
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR35 papers
- Centre National de la Recherche ScientifiqueFR21 papers
- Centre Lasers Intenses et ApplicationsFR14 papers
- Université de BordeauxFR12 papers
- Institut de Mathématiques de BordeauxFR11 papers
- Institut national de recherche en sciences et technologies du numériqueFR8 papers
- École PolytechniqueFR7 papers
- CEA DAM Île-de-FranceFR6 papers
- Laboratoire pour l'Utilisation des Lasers IntensesFR6 papers
- Sorbonne UniversitéFR6 papers
- Centre Inria de l'université de BordeauxFR5 papers
- Institut Polytechnique de BordeauxFR4 papers
57 papers
Parallel gradient boosting for flexible estimation of conditional distributions
Rémy Chapelle, Nicolas Vayatis, Bruno Falissard +1
Boosting is one of the most successful learning techniques for standard classification and regression tasks. Its extension to multi-output prediction problems has found an increasi…
All in one: holographic microscopy unveils bacterial transport from single cells to population
Lucie Klopffer, S. Becker, Laurence Mathieu +1
Prior to pioneer surface adhesion, bacteria have to navigate in flows, often in confined environments. While much is known about their individual swimming dynamics, our understandi…
Evaluating multi-season occupancy models with autocorrelation fitted to heterogeneous datasets
André Luís Luza, Didier Alard, Frédéric Barraquand
Predicting species distributions using occupancy models accounting for imperfect detection is now commonplace in ecology. Recently, modeling spatial and temporal autocorrelation wa…
Identifying Locally Turbulent Vortices within Instabilities
Fabien Vivodtzev, Florent Nauleau, Jean-Philippe Braeunig +1
This work presents an approach for the automatic detection of locally turbulent vortices within turbulent 2D flows such as instabilites. First, given a time step of the flow, metho…
Convergence of the Iterates for Momentum and RMSProp for Local Smooth Functions: Adaptation is the Key
Bilel Bensaid, Gaël Poëtte, Rodolphe Turpault
Both accelerated and adaptive gradient methods are among state of the art algorithms to train neural networks. The tuning of hyperparameters is needed to make them work efficiently…
An Abstract Lyapunov Control Optimizer: Local Stabilization and Global Convergence
Bilel Bensaid, Gaël Poëtte, Rodolphe Turpault
Recently, many machine learning optimizers have been analysed considering them as the asymptotic limit of some differential equations when the step size goes to zero. In other word…